47 citations · 87 across the 16 of their papers we have counts for
16 papers
Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning
Lijun Zhang, Xiao Liu, Kaleel Mahmood +2
Visual content understanding frequently relies on multi-task models to extract robust representations of a single visual input for multiple downstream tasks. However, in comparison…
Structured Pruning for Multi-Task Deep Neural Networks
Siddhant Garg, Lijun Zhang, Hui Guan
Although multi-task deep neural network (DNN) models have computation and storage benefits over individual single-task DNN models, they can be further optimized via model compressi…
GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism
Sandeep Polisetty, Juelin Liu, Kobi Falus +4
Graph neural networks (GNNs), an emerging class of machine learning models for graphs, have gained popularity for their superior performance in various graph analytical tasks. Mini…
Automatically Marginalized MCMC in Probabilistic Programming
Jinlin Lai, Javier Burroni, Hui Guan +1
Hamiltonian Monte Carlo (HMC) is a powerful algorithm to sample latent variables from Bayesian models. The advent of probabilistic programming languages (PPLs) frees users from wri…
Flow: Per-Instance Personalized Federated Learning Through Dynamic Routing
Kunjal Panchal, Sunav Choudhary, Nisarg Parikh +2
Personalization in Federated Learning (FL) aims to modify a collaboratively trained global model according to each client. Current approaches to personalization in FL are at a coar…
Uplifting Message Passing Neural Network with Graph Original Information
Xiao Liu, Lijun Zhang, Hui Guan
Message passing neural networks (MPNNs) learn the representation of graph-structured data based on graph original information, including node features and graph structures, and hav…
Improving Subgraph Representation Learning via Multi-View Augmentation
Yili Shen, Xiao Liu, Cheng-Wei Ju +4
Subgraph representation learning based on Graph Neural Network (GNN) has exhibited broad applications in scientific advancements, such as predictions of molecular structure-propert…
A Tree-Structured Multi-Task Model Recommender
Lijun Zhang, Xiao Liu, Hui Guan
Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL). The major challenge is to determine…
Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression
Yuezhou Sun, Wenlong Zhao, Lijun Zhang +3
This paper investigates deep neural network (DNN) compression from the perspective of compactly representing and storing trained parameters. We explore the previously overlooked op…
COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression
Sian Jin, Chengming Zhang, Xintong Jiang +5
Training wide and deep neural networks (DNNs) require large amounts of storage resources such as memory because the intermediate activation data must be saved in the memory during…
AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning
Lijun Zhang, Xiao Liu, Hui Guan
Multi-task learning (MTL) jointly learns a set of tasks by sharing parameters among tasks. It is a promising approach for reducing storage costs while improving task accuracy for m…
Rethinking Hard-Parameter Sharing in Multi-Domain Learning
Lijun Zhang, Qizheng Yang, Xiao Liu +1
Hard parameter sharing in multi-domain learning (MDL) allows domains to share some of the model parameters to reduce storage cost while improving prediction accuracy. One common sh…
Scalable Graph Neural Network Training: The Case for Sampling
Marco Serafini, Hui Guan
Graph Neural Networks (GNNs) are a new and increasingly popular family of deep neural network architectures to perform learning on graphs. Training them efficiently is challenging…
SID-NISM: A Self-supervised Low-light Image Enhancement Framework
Lijun Zhang, Xiao Liu, Erik Learned-Miller +1
When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenera…
Post-Training 4-bit Quantization on Embedding Tables
Hui Guan, Andrey Malevich, Jiyan Yang +2
Continuous representations have been widely adopted in recommender systems where a large number of entities are represented using embedding vectors. As the cardinality of the entit…
In-Place Zero-Space Memory Protection for CNN
Hui Guan, Lin Ning, Zhen Lin +3
Convolutional Neural Networks (CNN) are being actively explored for safety-critical applications such as autonomous vehicles and aerospace, where it is essential to ensure the reli…